{"id":"https://openalex.org/W3023701936","doi":"https://doi.org/10.48550/arxiv.1805.07918","title":"Primal-Dual Distributed Temporal Difference Learning","display_name":"Primal-Dual Distributed Temporal Difference Learning","alternate_titles":[],"publication_year":2018,"publication_date":"2018-05-21","ids":{"openalex":"https://openalex.org/W3023701936","doi":"https://doi.org/10.48550/arxiv.1805.07918","mag":"3023701936"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1805.07918","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.07918","pdf_url":"https://arxiv.org/pdf/1805.07918","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"parent_works":[],"lineage":["https://openalex.org/W3023701936"],"child_works_count":0,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1805.07918","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100654317","display_name":"Donghwan Lee","orcid":"https://orcid.org/0000-0002-4962-8478","observed_orcids":["https://orcid.org/0000-0002-4962-8478","https://orcid.org/0009-0006-4719-0042"]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Lee, Donghwan","raw_affiliation_strings":["Department of Electrical Engineering, KAIST, Daejeon, 34141, South Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, KAIST, Daejeon, 34141, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035753295","display_name":"Jianghai Hu","orcid":"https://orcid.org/0000-0002-4250-8852","observed_orcids":["https://orcid.org/0000-0002-4250-8852"]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"contributor_roles":[],"raw_author_name":"Hu, Jianghai","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47906, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Purdue University, West Lafayette, IN 47906, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8964999914169312,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.8964999914169312,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.0812000036239624,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.015300000086426735,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/multi-agent-markov-decision-process","display_name":"multi-agent Markov decision process","score":0.9950000047683716},{"id":"https://openalex.org/keywords/primal-dual-optimization","display_name":"primal-dual optimization","score":0.7059999704360962},{"id":"https://openalex.org/keywords/stochastic-optimization","display_name":"stochastic optimization","score":0.5799999833106995},{"id":"https://openalex.org/keywords/value-function-estimation","display_name":"value function estimation","score":0.7390000224113464},{"id":"https://openalex.org/keywords/constrained-convex-optimization","display_name":"constrained convex optimization","score":0.7699999809265137},{"id":"https://openalex.org/keywords/convergence-analysis","display_name":"convergence analysis","score":0.7639999985694885},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5669999718666077}],"concepts":[{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.8655308485031128},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8443563580513},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7041946649551392},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6831660270690918},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6162770390510559},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6048594117164612},{"id":"https://openalex.org/C145446738","wikidata":"https://www.wikidata.org/wiki/Q319913","display_name":"Convex function","level":3,"score":0.5770219564437866},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5732132196426392},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5170086622238159},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.48792359232902527},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4656902551651001},{"id":"https://openalex.org/C157972887","wikidata":"https://www.wikidata.org/wiki/Q463359","display_name":"Convex optimization","level":3,"score":0.42092105746269226},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.38122880458831787},{"id":"https://openalex.org/C112680207","wikidata":"https://www.wikidata.org/wiki/Q714886","display_name":"Regular polygon","level":2,"score":0.3349970281124115},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29141765832901},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2880818545818329},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1805.07918","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.07918","pdf_url":"https://arxiv.org/pdf/1805.07918","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2803863885","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1805.07918v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1805.07918","doi":"https://doi.org/10.48550/arxiv.1805.07918","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1805.07918","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1805.07918","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.07918","pdf_url":"https://arxiv.org/pdf/1805.07918","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3023701936.pdf","grobid_xml":"https://content.openalex.org/works/W3023701936.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W359568995","https://openalex.org/W1409984952","https://openalex.org/W1499021337","https://openalex.org/W1515851193","https://openalex.org/W1571416372","https://openalex.org/W1576452626","https://openalex.org/W1630241696","https://openalex.org/W1646707810","https://openalex.org/W1706236309","https://openalex.org/W1835716857","https://openalex.org/W1918371733","https://openalex.org/W1987717935","https://openalex.org/W1992208280","https://openalex.org/W2012106138","https://openalex.org/W2020123437","https://openalex.org/W2026509976","https://openalex.org/W2040125997","https://openalex.org/W2070291355","https://openalex.org/W2075268401","https://openalex.org/W2105850748","https://openalex.org/W2106471678","https://openalex.org/W2106901427","https://openalex.org/W2114791779","https://openalex.org/W2121863487","https://openalex.org/W2144672231","https://openalex.org/W2156737235","https://openalex.org/W2164642931","https://openalex.org/W2165744313","https://openalex.org/W2216483973","https://openalex.org/W2293415235","https://openalex.org/W2296319761","https://openalex.org/W2496350169","https://openalex.org/W2504148212","https://openalex.org/W2562316362","https://openalex.org/W2763533254","https://openalex.org/W2788115019","https://openalex.org/W2793630680","https://openalex.org/W2798766386","https://openalex.org/W2805324628","https://openalex.org/W2913483008","https://openalex.org/W2944956041","https://openalex.org/W2963470657","https://openalex.org/W2963550797","https://openalex.org/W2966162740","https://openalex.org/W2966952338","https://openalex.org/W3029957720","https://openalex.org/W3119097918","https://openalex.org/W3139377883","https://openalex.org/W3153787838","https://openalex.org/W4214717370","https://openalex.org/W4254313632","https://openalex.org/W4307347247"],"related_works":["https://openalex.org/W2793630680","https://openalex.org/W4312657794","https://openalex.org/W4414359257","https://openalex.org/W2966162740","https://openalex.org/W4321768300","https://openalex.org/W3036250521","https://openalex.org/W2944956041","https://openalex.org/W2504148212","https://openalex.org/W3101698686"],"abstract_inverted_index":{"The":[0,27,71],"goal":[1],"of":[2,11,21,89,97,131,133],"this":[3,93],"paper":[4],"is":[5,31,103],"to":[6,79,86,119,128],"study":[7],"a":[8,19,32,49,64,68,106,114,129],"distributed":[9,117],"version":[10],"the":[12,54,58,81,87,95,99,125,134],"gradient":[13],"temporal-difference":[14,28],"(GTD)":[15],"learning":[16,30,34],"algorithm":[17,36,118,126],"for":[18,48],"class":[20],"multi-agent":[22,59],"Markov":[23],"decision":[24],"processes":[25],"(MDPs).":[26],"(TD)":[29],"reinforcement":[33],"(RL)":[35],"that":[37,124],"learns":[38],"an":[39],"infinite":[40],"horizon":[41],"discounted":[42],"cost":[43],"function":[44,84,102],"(or":[45],"value":[46,83,101],"function)":[47],"given":[50],"fixed":[51],"policy":[52],"without":[53],"model":[55],"knowledge.":[56],"In":[57,92],"MDP":[60],"each":[61],"agent":[62],"receives":[63],"local":[65,69,90],"reward":[66],"through":[67],"processing.":[70],"agents":[72],"communicate":[73],"over":[74],"sparse":[75],"and":[76,122],"random":[77],"networks":[78],"learn":[80],"global":[82,100],"corresponding":[85],"aggregate":[88],"rewards.":[91],"paper,":[94],"problem":[96],"estimating":[98],"converted":[104],"into":[105],"constrained":[107],"convex":[108],"optimization":[109,135],"problem.":[110,136],"Then,":[111],"we":[112],"propose":[113],"stochastic":[115],"primal-dual":[116],"solve":[120],"it":[121],"prove":[123],"converges":[127],"set":[130],"solutions":[132]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W3023701936","counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-11-21T10:27:49.728292","created_date":"2020-05-13T00:00:00"}
